文章基本信息

标题：A Machine Learning Method for Detecting Line Defects of Glass Substrates Using Time Series Non-contact Line Scan Data
本地全文：下载
作者：Kazuki Ota ; Hideki Katagiri
期刊名称：Lecture Notes in Engineering and Computer Science
印刷版ISSN：2078-0958
电子版ISSN：2078-0966
出版年度：2019
卷号：2241
页码：287-292
出版社：Newswood and International Association of Engineers
摘要：Recently, the demand for ultra-high definition with 4K and 8K panels has increased. The study in this paper develops a fast algorithm for detecting wiring defects of glass substrates, which is based on an analysis done on time series data obtained through non-contact electronic inspection. New feature quantities with respect to the frequency domain of time series data are proposed. To demonstrate the effectiveness of the proposed algorithm, numerical experiments are conducted using the real sensing data obtained in the field of glass substrate inspection.
关键词：defect detection; machine learning; glass substrate; time series data; non;contact inspection; frequencydomain feature